© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75291
    Prev
    Next
    INDEX
    Explanations

    plans to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ၚ
    0.35
     "",
    0.32
     Monastery
    0.32
     Presents
    0.31
     cubes
    0.30
     survival
    0.30
     poverty
    0.30
     screening
    0.30
    芜
    0.29
     block
    0.29
    POSITIVE LOGITS
    Exc
    0.36
    ettin
    0.35
    otta
    0.33
    тят
    0.33
     ডিভিশ
    0.33
     යා
    0.33
    ᾧ
    0.32
     başvur
    0.32
    alarına
    0.32
    itts
    0.32
    Activations Density 0.002%

    No Known Activations